There is still a dearth of systematic study on picture stitching techniques for the natural tubular structures of intestines,and traditional stitching techniques have a poor application to endoscopic images with deep ...There is still a dearth of systematic study on picture stitching techniques for the natural tubular structures of intestines,and traditional stitching techniques have a poor application to endoscopic images with deep scenes.In order to recreate the intestinal wall in two dimensions,a method is developed.The normalized Laplacian algorithm is used to enhance the image and transform it into polar coordinates according to the characteristics that intestinal images are not obvious and usually arranged in a circle,in order to extract the new image segments of the current image relative to the previous image.The improved weighted fusion algorithm is then used to sequentially splice the segment images.The experimental results demonstrate that the suggested approach can improve image clarity and minimize noise while maintaining the information content of intestinal images.In addition,the method's seamless transition between the final portions of a panoramic image also demonstrates that the stitching trace has been removed.展开更多
The unmanned aerial vehicle(UAV)images captured under low-light conditions are often suffering from noise and uneven illumination.To address these issues,we propose a low-light image enhancement algorithm for UAV imag...The unmanned aerial vehicle(UAV)images captured under low-light conditions are often suffering from noise and uneven illumination.To address these issues,we propose a low-light image enhancement algorithm for UAV images,which is inspired by the Retinex theory and guided by a light weighted map.Firstly,we propose a new network for reflectance component processing to suppress the noise in images.Secondly,we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process.Finally,the processed reflectance and illumination components are recombined to obtain the enhancement results.Experimental results show that our method can suppress the noise in images while enhancing image brightness,and prevent over enhancement in bright regions.Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.展开更多
Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing method...Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing methods often fail to distinguish salient objects from background regions,leading to detail suppression in salient regions due to global fusion strategies.This study presents a mask-guided latent low-rank representation fusion method to address this issue.First,the GrabCut algorithm is employed to extract a saliency mask,distinguishing salient regions from background regions.Then,latent low-rank representation(LatLRR)is applied to extract deep image features,enhancing key information extraction.In the fusion stage,a weighted fusion strategy strengthens infrared thermal information and visible texture details in salient regions,while an average fusion strategy improves background smoothness and stability.Experimental results on the TNO dataset demonstrate that the proposed method achieves superior performance in SPI,MI,Qabf,PSNR,and EN metrics,effectively preserving salient target details while maintaining balanced background information.Compared to state-of-the-art fusion methods,our approach achieves more stable and visually consistent fusion results.The fusion code is available on GitHub at:https://github.com/joyzhen1/Image(accessed on 15 January 2025).展开更多
To improve image quality under low illumination conditions,a novel low-light image enhancement method is proposed in this paper based on multi-illumination estimation and multi-scale fusion(MIMS).Firstly,the illuminat...To improve image quality under low illumination conditions,a novel low-light image enhancement method is proposed in this paper based on multi-illumination estimation and multi-scale fusion(MIMS).Firstly,the illumination is processed by contrast-limited adaptive histogram equalization(CLAHE),adaptive complementary gamma function(ACG),and adaptive detail preserving S-curve(ADPS),respectively,to obtain three components.Then,the fusion-relevant features,exposure,and color contrast are selected as the weight maps.Subsequently,these components and weight maps are fused through multi-scale to generate enhanced illumination.Finally,the enhanced images are obtained by multiplying the enhanced illumination and reflectance.Compared with existing approaches,this proposed method achieves an average increase of 0.81%and 2.89%in the structural similarity index measurement(SSIM)and peak signal-to-noise ratio(PSNR),and a decrease of 6.17%and 32.61%in the natural image quality evaluator(NIQE)and gradient magnitude similarity deviation(GMSD),respectively.展开更多
Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morp...Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morphology is to use construction ele- ment measure image morphology for solving understand problem.The article presented advanced cellular neural network that forms mathematical morphological cellular neural network (MMCNN) equation to be suit for mathematical morphology filter.It gave the theo- ries of MMCNN dynamic extent and stable state.It is evidenced that arrived mathematical morphology filter through steady of dynamic process in definite condition.展开更多
The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is propos...The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.展开更多
BACKGROUND It is evident that an accurate evaluation of T and N stage rectal cancer is essential for treatment planning.It has not been extensively investigated whether texture features derived from diffusion-weighted...BACKGROUND It is evident that an accurate evaluation of T and N stage rectal cancer is essential for treatment planning.It has not been extensively investigated whether texture features derived from diffusion-weighted imaging(DWI)images and apparent diffusion coefficient(ADC)maps are associated with the extent of local invasion(pathological stage T1-2 vs T3-4)and nodal involvement(pathological stage N0 vs N1-2)in rectal cancer.AIM To predict different stages of rectal cancer using texture analysis based on DWI images and ADC maps.METHODS One hundred and fifteen patients with pathologically proven rectal cancer,who underwent preoperative magnetic resonance imaging,including DWI,were enrolled,retrospectively.The ADC measurements(ADCmean,ADCmin,ADCmax)as well as texture features,including the gray level co-occurrence matrix parameters,the gray level run-length matrix parameters and wavelet parameters were calculated based on DWI(b=0 and b=1000)images and the ADC maps.Independent sample t-tests or Mann-Whitney U tests were used for statistical analysis.Multivariate logistic regression analysis was conducted to establish the models.The predictive performance was validated by receiver operating characteristic curve analysis.RESULTS Dissimilarity,sum average,information correlation and run-length nonuniformity from DWIb=0 images,gray level nonuniformity,run percentage and run-length nonuniformity from DWIb=1000 images,and dissimilarity and run percentage from ADC maps were found to be independent predictors of local invasion(stage T3-4).The area under the operating characteristic curve of the model reached 0.793 with a sensitivity of 78.57%and a specificity of 74.19%.Sum average,gray level nonuniformity and the horizontal components of symlet transform(SymletH)from DWIb=0 images,sum average,information correlation,long run low gray level emphasis and SymletH from DWIb=1000 images,and ADCmax,ADCmean and information correlation from ADC maps were identified as independent predictors of nodal involvement.The area under the operating characteristic curve of the model reached 0.802 with a sensitivity of 80.77%and a specificity of 68.25%.CONCLUSION Texture features extracted from DWI images and ADC maps are useful clues for predicting pathological T and N stages in rectal cancer.展开更多
The recent advances in remote sensing and computer techniques give birth to the explosive growth of remote sensing images.The emergence of cloud storage has brought new opportunities for storage and management of mass...The recent advances in remote sensing and computer techniques give birth to the explosive growth of remote sensing images.The emergence of cloud storage has brought new opportunities for storage and management of massive remote sensing images with its large storage space,cost savings.However,the openness of cloud brings challenges for image data security.In this paper,we propose a weighted image sharing scheme to ensure the security of remote sensing in cloud environment,which takes the weights of participants(i.e.,cloud service providers)into consideration.An extended Mignotte sequence is constructed according to the weights of participants,and we can generate image shadow shares based on the hash value which can be obtained from gray value of remote sensing images.Then we store the shadows in every cloud service provider,respectively.At last,we restore the remote sensing image based on the Chinese Remainder Theorem.Experimental results show the proposed scheme can effectively realize the secure storage of remote sensing images in the cloud.The experiment also shows that no matter weight values,each service providers only needs to save one share,which simplifies the management and usage,it also reduces the transmission of secret information,strengthens the security and practicality of this scheme.展开更多
The nonlocal means( NLM) has been widely used in image processing. In this paper,we introduce a modified weight function for NLM denoising, which will compute the nonlocal similarities among the pre-processing pixel p...The nonlocal means( NLM) has been widely used in image processing. In this paper,we introduce a modified weight function for NLM denoising, which will compute the nonlocal similarities among the pre-processing pixel patches instead of the commonly used similarity measure based on noisy observations. By the law of large number,the norm for the pre-processing pixel patches is closer to the norm of the original clean pixel patches,so the proposed weight functions are more optimized and the selected similar patches are more accurate. Experimental results indicate the proposed algorithm achieves better restored results compared to the classical NLM's method.展开更多
Objective： To assess if diffusion-weighted magnetic resonance （MR） imaging without apparent diffusion coefficient （ADC） values provides added diagnostic value in combination with conventional MR imaging in the de...Objective： To assess if diffusion-weighted magnetic resonance （MR） imaging without apparent diffusion coefficient （ADC） values provides added diagnostic value in combination with conventional MR imaging in the detection and characterization of small nodules in cirrhotic liver. Methods： Two observers retrospectively and independently analyzed 86 nodules （_〈3 em） certified pathologically in 33 patients with liver cirrhosis, including 48 hepatocellular carcinoma （HCC） nodules, 13 high-grade dysplastic nodules （HDN）, 10 low-grade dysplastic nodules （LDNs） and 15 other benign nodules. All these focal nodules were evaluated with conventional MR images （Tl-weighted, T2-weighted and dynamic gadolinium-enhanced images） and breath-hold diffusion-weighted images （DWI） （b=500 s/mm2）. The nodules were classified by using a scale of 1-3 （1, not seen; 3, well seen） on DWI for qualitative assessment. These small nodules were characterized by two radiologists. ADC values weren＇t measured. The diagnostic performance of the combined DWI-conventional images and the conventional images alone was evaluated using receiver operating characteristic （ROC） curves. The area under the curves （Az）, sensitivity and specificity values for characterizing different small nodules were also calculated. Results： Among 48 HCC nodules, 33 （68.8%） were graded as 3 （well seen）, 6 （12.5%） were graded as 2 （partially obscured）, and 9 weren＇t seen on DWI. Among 13 HDNs, there were 3 （23.1%） and 4 （30.8%） graded as 3 and 2 respectively. Five （50%） of 10 benign nodules were partially obscured and slightly hyperintense. For 86 nodules, the average diagnostic accuracy of combined DWI-conventional images was 82.56%, which was increased significantly compared with conventional MR images with 76.17%. For HCC and HDN, the diagnostic accuracy of combined DWI-conventional images increased from 78.69% to 86.07 %. Conclusions： Diffusion-weighted MR imaging does provide added diagnostic value in the detection and characterization of HDN and HCC, and it may not be helpful for LDN and regenerative nodule （RN） in cirrhotic liver.展开更多
Objective To assess the reproducibility of whole-body diffusion weighted imaging(WB-DWI) technique in healthy volunteers under normal breathing with background body signal suppression.Methods WB-DWI was performed on 3...Objective To assess the reproducibility of whole-body diffusion weighted imaging(WB-DWI) technique in healthy volunteers under normal breathing with background body signal suppression.Methods WB-DWI was performed on 32 healthy volunteers twice within two-week period using short TI inversion-recovery diffusion-weighted echo-planar imaging sequence and built-in body coil.The volunteers were scanned across six stations continuously covering the entire body from the head to the feet under normal breathing.The bone apparent diffusion coefficient(ADC) and exponential ADC(eADC) of regions of interest(ROIs) were measured.We analyzed correlation of the results using paired-t-test to assess the reproducibility of the WB-DWI technique.Results We were successful in collecting and analyzing data of 64 WB-DWI images.There was no significant difference in bone ADC and eADC of 824 ROIs between the paired observers and paired scans(P>0.05).Most of the images from all stations were of diagnostic quality.Conclusion The measurements of bone ADC and eADC have good reproducibility.WB-DWI technique under normal breathing with background body signal suppression is adequate.展开更多
Particle size distribution of coarse aggregates through mechanical sieving gives results in terms of cumu- lative mass percent. But digital image processing generated size distribution of particles, while being fast a...Particle size distribution of coarse aggregates through mechanical sieving gives results in terms of cumu- lative mass percent. But digital image processing generated size distribution of particles, while being fast and accurate, is often expressed in terms of area function or number of particles. In this paper, a mass model is developed which converts the image obtained size distribution to mass-wise distribution, mak- ing it readily comparable to mechanical sieving data. The concept of weight/particle ratio is introduced for mass reconstruction from 2D images of particle aggregates. Using this mass model, the effects of several particle shape parameters （such as major axis, minor axis, and equivalent diameter） on sieve-size of the particles is studied. It is shown that the sieve-size of a particle strongly depend upon the shape param- eters, 91% of its variation being explained by major axis, minor axis, bounding box length and equivalent diameter. Furthermore, minor axis gives an overall accurate estimate of particle sieve-size, error in mean size （D-50） being just 0.4%. However, sieve-size of smaller particles （〈20 ram） strongly depends upon the length of the smaller arm of the bounding box enclosing them and sieve-sizes of larger particles （〉20 mm） are highly correlated to their equivalent diameters. Multiple linear regression analysis has been used to generate overall mass-wise particle size distribution, considering the influences of all these shape parameters on particle sieve-size. Multiple linear regression generated overall mass-wise particle size distribution shows a strong correlation with sieve generated data. The adjusted R-square value of the regression analysis is found to be 99 percent （w.r,t cumulative frequency）. The method proposed in this paper provides a time-efficient way of producing accurate （up to 99%） mass-wise PSD using digital image processing and it can be used effectively to renlace the mechanical sieving.展开更多
Regularization methods have been substantially applied in image restoration due to the ill-posedness of the image restoration problem.Different assumptions or priors on images are applied in the construction of image ...Regularization methods have been substantially applied in image restoration due to the ill-posedness of the image restoration problem.Different assumptions or priors on images are applied in the construction of image regularization methods.In recent years,matrix low-rank approximation has been successfully introduced in the image denoising problem and significant denoising effects have been achieved.Low-rank matrix minimization is an NP-hard problem and it is often replaced with the matrix’s weighted nuclear norm minimization(WNNM).The assumption that an image contains an extensive amount of self-similarity is the basis for the construction of the matrix low-rank approximation-based image denoising method.In this paper,we develop a model for image restoration using the sum of block matching matrices’weighted nuclear norm to be the regularization term in the cost function.An alternating iterative algorithm is designed to solve the proposed model and the convergence analyses of the algorithm are also presented.Numerical experiments show that the proposed method can recover the images much better than the existing regularization methods in terms of both recovered quantities and visual qualities.展开更多
In the domain ofmedical imaging,the accurate detection and classification of brain tumors is very important.This study introduces an advanced method for identifying camouflaged brain tumors within images.Our proposed ...In the domain ofmedical imaging,the accurate detection and classification of brain tumors is very important.This study introduces an advanced method for identifying camouflaged brain tumors within images.Our proposed model consists of three steps:Feature extraction,feature fusion,and then classification.The core of this model revolves around a feature extraction framework that combines color-transformed images with deep learning techniques,using the ResNet50 Convolutional Neural Network(CNN)architecture.So the focus is to extract robust feature fromMRI images,particularly emphasizingweighted average features extracted fromthe first convolutional layer renowned for their discriminative power.To enhance model robustness,we introduced a novel feature fusion technique based on the Marine Predator Algorithm(MPA),inspired by the hunting behavior of marine predators and has shown promise in optimizing complex problems.The proposed methodology can accurately classify and detect brain tumors in camouflage images by combining the power of color transformations,deep learning,and feature fusion via MPA,and achieved an accuracy of 98.72%on a more complex dataset surpassing the existing state-of-the-art methods,highlighting the effectiveness of the proposed model.The importance of this research is in its potential to advance the field ofmedical image analysis,particularly in brain tumor diagnosis,where diagnoses early,and accurate classification are critical for improved patient results.展开更多
As synthetic aperture radar（SAR） has been widely used nearly in every field, SAR image de-noising became a very important research field. A new SAR image de-noising method based on texture strength and weighted nucl...As synthetic aperture radar（SAR） has been widely used nearly in every field, SAR image de-noising became a very important research field. A new SAR image de-noising method based on texture strength and weighted nuclear norm minimization（WNNM） is proposed. To implement blind de-noising, the accurate estimation of noise variance is very important. So far, it is still a challenge to estimate SAR image noise level accurately because of the rich texture. Principal component analysis（PCA） and the low rank patches selected by image texture strength are used to estimate the noise level. With the help of noise level, WNNM can be expected to SAR image de-noising. Experimental results show that the proposed method outperforms many excellent de-noising algorithms such as Bayes least squares-Gaussian scale mixtures（BLS-GSM） method, non-local means（NLM） filtering in terms of both quantitative measure and visual perception quality.展开更多
Summary： The chronological and spatial rules of changes during focal cerebral ischemia and reperfusion in different brain regions with magnetic resonance diffusion-weighted imaging （DWI） in a model of occlusion of ...Summary： The chronological and spatial rules of changes during focal cerebral ischemia and reperfusion in different brain regions with magnetic resonance diffusion-weighted imaging （DWI） in a model of occlusion of middle cerebral artery （MCAO） and the development of cytotoxic edema in acute phase were explored. Fifteen healthy S-D rats with MCA occluded by thread-emboli were randomly divided into three groups. 15 min after the operation, the serial imaging was scanned on DWI for the three groups. The relative mean signal intensity （RMSI） of the frontal lobe, parietal lobe, lateral cauda-putamen, medial cauda-putamen and the volume of regions of hyperintense signal on DWI were calculated. After the last DWI scanning, T2WI was performed for the three groups. After 15 rain ischemia, the rats was presented hyperintense signals on DWI. The regions of hyperintense signal were enlarged with prolonging ischemia time. The regions of hyperintense signal were back to normal after 60 min reperfusion with a small part remaining to show hyperintense signal. The RMSIs of parietal lobe and lateral cauda-putamen were higher than that of the frontal lobe and medial cauda-putamen both in ischemia phase and recanalization phase. The three groups were normal on T2WI imaging. DWI had good sensitivity to acute cerebral ischemia, which was used to study the chronological and spatial rules of development of early cell edema in ischemia regions.展开更多
To denoise the diffusion weighted images （DWls） featured as multi-boundary, which was very important for the calculation of accurate DTIs （diffusion tensor magnetic resonance imaging）, a modified Wiener filter was...To denoise the diffusion weighted images （DWls） featured as multi-boundary, which was very important for the calculation of accurate DTIs （diffusion tensor magnetic resonance imaging）, a modified Wiener filter was proposed. Through analyzing the widely accepted adaptive Wiener filter in image denoising fields, which suffered from annoying noise around the edges of DWIs and in turn greatly affected the denoising effect of DWIs, a local-shift method capable of overcoming the defect of the adaptive Wiener filter was proposed to help better denoising DWIs and the modified Wiener filter was constructed accordingly. To verify the denoising effect of the proposed method, the modified Wiener filter and adaptive Wiener filter were performed on the noisy DWI data, respectively, and the results of different methods were analyzed in detail and put into comparison. The experimental data show that, with the modified Wiener method, more satisfactory results such as lower non-positive tensor percentage and lower mean square errors of the fractional anisotropy map and trace map are obtained than those with the adaptive Wiener method, which in turn helps to produce more accurate DTIs.展开更多
In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted av...In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted averaging pixel values in consecutive frames, this algorithm achieves the filtering goal by assigning smaller weights to the pixels with inappropriate estimated motion trajectory for noise. It only utilizes the intensity of pixels to suppress noise and accordingly is independent of noise variance. To evaluate the performance of the proposed filtering algorithm, its mean square error and percentage of preserved edge points were compared with those of traditional adaptive weighted averaging and non-adaptive mean filtering algorithms under different noise variances. Relevant results show that the MAWA filtering algorithm can preserve image structures and edges under motion after attenuating noise, and thus may be used in image sequence filtering.展开更多
Medical linac based imaging modalities such as portal imaging can be utilized for highly accurate measurements. An intensity-weighted centroid method for determining object center is proposed that can detect the posit...Medical linac based imaging modalities such as portal imaging can be utilized for highly accurate measurements. An intensity-weighted centroid method for determining object center is proposed that can detect the position of small object at subpixel accuracy. The principles and algorithms of the intensity-weighted centroid method are presented. Analytical results are derived for positional accuracy of a rod and a sphere in digital images, and the theoretical accuracy limits are calculated. The method was experimentally examined using phantoms with embedded ball bearings (BBs). Images of the phantoms were taken by the MV portal imager of a medical linac. The image pixel size was 0.26 mm when projected at the linac isocenter plane. The BB coordinates were calculated by applying the intensity-weighted centroid method after removing the background. The reproducibility of BB position detection was measured with 3 monitor unit (MU) exposures at various dose rates. A stationary BB, of 0.25 image contrast, showed position reproducibility in the range of 0.004 - 0.013 mm. When the method was used to measure the displacement of a moving BB, the difference between the measured and expected BB position had a standard deviation of 0.006 mm. The effect of image noise on the BB detection accuracy was measured using a phantom with multiple BBs. The overall detection accuracy, represented by standard deviation, steadily improved from 0.13 mm at 0.03 MU to 0.008 mm at 5.0 MU, and showed an inverse correlation with contrast-to-noise ratio. We demonstrated that intensity-weighted centroid method can achieve subpixel accuracy in position detection. With a linac based imaging system, precise mechanical measurement with accuracy of microns could be achieved.展开更多
BACKGROUND Cutaneous melanoma is an aggressive skin cancer with high metastatic potential.Accurate staging is critical to guide therapeutic strategies and improve prognosis.Whole-body magnetic resonance imaging(WB-MRI...BACKGROUND Cutaneous melanoma is an aggressive skin cancer with high metastatic potential.Accurate staging is critical to guide therapeutic strategies and improve prognosis.Whole-body magnetic resonance imaging(WB-MRI),particularly when combined with diffusion-weighted imaging(DWI),has emerged as promising tool for comprehensive,radiation-free assessment of metastatic spread.AIM To systematically review the diagnostic performance and clinical utility of WBMRI in the staging and restaging of cutaneous melanoma,with comparison to conventional imaging modalities such as computed tomography(CT)and positron emission tomography/CT(PET/CT).METHODS A systematic literature review was conducted using PubMed,Embase,Scopus and Web of Science databases for studies published in the last 10 years.Inclusion criteria focused on comparative diagnostic accuracy studies of WB-MRI vs CT and PET/CT for melanoma staging.The methodological quality of the studies was appraised using the QUADAS-2 tool.RESULTS Sixteen studies involving over 700 patients met the inclusion criteria.WB-MRI showed high sensitivity(73%-90%)and specificity(up to 98%)in detecting metastases,particularly in bone,liver and soft tissue.DWI enhanced lesion detection,and WB-MRI often influenced clinical management decisions.However,CT outperformed WB-MRI in identifying small pulmonary nodules.AI-assisted analysis and contrastenhanced sequences further improved diagnostic confidence.CONCLUSION WB-MRI represents a robust imaging modality for staging cutaneous melanoma,offering superior soft-tissue contrast and functional imaging without ionizing radiation.Its strengths lie in detecting bone,liver and brain metastases.Challenges include limited lung lesion detection,cost,and availability.Advances in artificial intelligence,Hybrid PET/MRY systems,and radiomics are poised to expand WB-MRI’s role in personalized melanoma management.展开更多
基金the Special Research Fund for the Natural Science Foundation of Chongqing(No.cstc2019jcyjmsxm1351)the Science and Technology Research Project of Chongqing Education Commission(No.KJQN2020006300)。
文摘There is still a dearth of systematic study on picture stitching techniques for the natural tubular structures of intestines,and traditional stitching techniques have a poor application to endoscopic images with deep scenes.In order to recreate the intestinal wall in two dimensions,a method is developed.The normalized Laplacian algorithm is used to enhance the image and transform it into polar coordinates according to the characteristics that intestinal images are not obvious and usually arranged in a circle,in order to extract the new image segments of the current image relative to the previous image.The improved weighted fusion algorithm is then used to sequentially splice the segment images.The experimental results demonstrate that the suggested approach can improve image clarity and minimize noise while maintaining the information content of intestinal images.In addition,the method's seamless transition between the final portions of a panoramic image also demonstrates that the stitching trace has been removed.
基金supported by the National Natural Science Foundation of China(Nos.62201454 and 62306235)the Xi’an Science and Technology Program of Xi’an Science and Technology Bureau(No.23SFSF0004)。
文摘The unmanned aerial vehicle(UAV)images captured under low-light conditions are often suffering from noise and uneven illumination.To address these issues,we propose a low-light image enhancement algorithm for UAV images,which is inspired by the Retinex theory and guided by a light weighted map.Firstly,we propose a new network for reflectance component processing to suppress the noise in images.Secondly,we construct an illumination enhancement module that uses a light weighted map to guide the enhancement process.Finally,the processed reflectance and illumination components are recombined to obtain the enhancement results.Experimental results show that our method can suppress the noise in images while enhancing image brightness,and prevent over enhancement in bright regions.Code and data are available at https://gitee.com/baixiaotong2/uav-images.git.
基金supported by Universiti Teknologi MARA through UiTM MyRA Research Grant,600-RMC 5/3/GPM(053/2022).
文摘Infrared and visible image fusion technology integrates the thermal radiation information of infrared images with the texture details of visible images to generate more informative fused images.However,existing methods often fail to distinguish salient objects from background regions,leading to detail suppression in salient regions due to global fusion strategies.This study presents a mask-guided latent low-rank representation fusion method to address this issue.First,the GrabCut algorithm is employed to extract a saliency mask,distinguishing salient regions from background regions.Then,latent low-rank representation(LatLRR)is applied to extract deep image features,enhancing key information extraction.In the fusion stage,a weighted fusion strategy strengthens infrared thermal information and visible texture details in salient regions,while an average fusion strategy improves background smoothness and stability.Experimental results on the TNO dataset demonstrate that the proposed method achieves superior performance in SPI,MI,Qabf,PSNR,and EN metrics,effectively preserving salient target details while maintaining balanced background information.Compared to state-of-the-art fusion methods,our approach achieves more stable and visually consistent fusion results.The fusion code is available on GitHub at:https://github.com/joyzhen1/Image(accessed on 15 January 2025).
基金supported by the National Key R&D Program of China(No.2022YFB3205101)NSAF(No.U2230116)。
文摘To improve image quality under low illumination conditions,a novel low-light image enhancement method is proposed in this paper based on multi-illumination estimation and multi-scale fusion(MIMS).Firstly,the illumination is processed by contrast-limited adaptive histogram equalization(CLAHE),adaptive complementary gamma function(ACG),and adaptive detail preserving S-curve(ADPS),respectively,to obtain three components.Then,the fusion-relevant features,exposure,and color contrast are selected as the weight maps.Subsequently,these components and weight maps are fused through multi-scale to generate enhanced illumination.Finally,the enhanced images are obtained by multiplying the enhanced illumination and reflectance.Compared with existing approaches,this proposed method achieves an average increase of 0.81%and 2.89%in the structural similarity index measurement(SSIM)and peak signal-to-noise ratio(PSNR),and a decrease of 6.17%and 32.61%in the natural image quality evaluator(NIQE)and gradient magnitude similarity deviation(GMSD),respectively.
文摘Mathematical morphology is widely applicated in digital image procesing.Vari- ary morphology construction and algorithm being developed are used in deferent digital image processing.The basic idea of mathematical morphology is to use construction ele- ment measure image morphology for solving understand problem.The article presented advanced cellular neural network that forms mathematical morphological cellular neural network (MMCNN) equation to be suit for mathematical morphology filter.It gave the theo- ries of MMCNN dynamic extent and stable state.It is evidenced that arrived mathematical morphology filter through steady of dynamic process in definite condition.
基金Supported by the National Natural Science Foundation of China (No. 60972106)Postdoctoral Science Foundation (No. 20090450750)the Science Foundation of Tianjin(No. 11JCYBJC00900)
文摘The priority of the filled patch play a key role in the exemplar-based image inpainting, and it should be determined firstly to optimize the process of image inpainting. A modified image inpainting algorithm is proposed by weighted-priority based on the Criminisi algorithm. The improved algorithm demonstrates better relationship between the data term and the confidence term for the optimization of the priority than the classical Criminisi algorithm. By comparing the effect of the inpainted images with different structure, conclusion can be drawn that the optimal priority should be chosen properly for different images with different structures.
基金Supported by Research and Development Foundation for Major Science and Technology from Shenyang,No.19-112-4-105Big Data Foundation for Health Care from China Medical University,No.HMB201902105Natural Fund Guidance Plan from Liaoning,No.2019-ZD-0743.
文摘BACKGROUND It is evident that an accurate evaluation of T and N stage rectal cancer is essential for treatment planning.It has not been extensively investigated whether texture features derived from diffusion-weighted imaging(DWI)images and apparent diffusion coefficient(ADC)maps are associated with the extent of local invasion(pathological stage T1-2 vs T3-4)and nodal involvement(pathological stage N0 vs N1-2)in rectal cancer.AIM To predict different stages of rectal cancer using texture analysis based on DWI images and ADC maps.METHODS One hundred and fifteen patients with pathologically proven rectal cancer,who underwent preoperative magnetic resonance imaging,including DWI,were enrolled,retrospectively.The ADC measurements(ADCmean,ADCmin,ADCmax)as well as texture features,including the gray level co-occurrence matrix parameters,the gray level run-length matrix parameters and wavelet parameters were calculated based on DWI(b=0 and b=1000)images and the ADC maps.Independent sample t-tests or Mann-Whitney U tests were used for statistical analysis.Multivariate logistic regression analysis was conducted to establish the models.The predictive performance was validated by receiver operating characteristic curve analysis.RESULTS Dissimilarity,sum average,information correlation and run-length nonuniformity from DWIb=0 images,gray level nonuniformity,run percentage and run-length nonuniformity from DWIb=1000 images,and dissimilarity and run percentage from ADC maps were found to be independent predictors of local invasion(stage T3-4).The area under the operating characteristic curve of the model reached 0.793 with a sensitivity of 78.57%and a specificity of 74.19%.Sum average,gray level nonuniformity and the horizontal components of symlet transform(SymletH)from DWIb=0 images,sum average,information correlation,long run low gray level emphasis and SymletH from DWIb=1000 images,and ADCmax,ADCmean and information correlation from ADC maps were identified as independent predictors of nodal involvement.The area under the operating characteristic curve of the model reached 0.802 with a sensitivity of 80.77%and a specificity of 68.25%.CONCLUSION Texture features extracted from DWI images and ADC maps are useful clues for predicting pathological T and N stages in rectal cancer.
基金This research was partly supported by(National Natural Science Foundation of China under 41671431,61572421and Shanghai Science and Technology Commission Project 15590501900.
文摘The recent advances in remote sensing and computer techniques give birth to the explosive growth of remote sensing images.The emergence of cloud storage has brought new opportunities for storage and management of massive remote sensing images with its large storage space,cost savings.However,the openness of cloud brings challenges for image data security.In this paper,we propose a weighted image sharing scheme to ensure the security of remote sensing in cloud environment,which takes the weights of participants(i.e.,cloud service providers)into consideration.An extended Mignotte sequence is constructed according to the weights of participants,and we can generate image shadow shares based on the hash value which can be obtained from gray value of remote sensing images.Then we store the shadows in every cloud service provider,respectively.At last,we restore the remote sensing image based on the Chinese Remainder Theorem.Experimental results show the proposed scheme can effectively realize the secure storage of remote sensing images in the cloud.The experiment also shows that no matter weight values,each service providers only needs to save one share,which simplifies the management and usage,it also reduces the transmission of secret information,strengthens the security and practicality of this scheme.
基金National Natural Science Foundations of China(Nos.U1504603,61301229)Key Scientific Research Project of Colleges and Universities in Henan Province,China(Nos.18A120002,19A110014)
文摘The nonlocal means( NLM) has been widely used in image processing. In this paper,we introduce a modified weight function for NLM denoising, which will compute the nonlocal similarities among the pre-processing pixel patches instead of the commonly used similarity measure based on noisy observations. By the law of large number,the norm for the pre-processing pixel patches is closer to the norm of the original clean pixel patches,so the proposed weight functions are more optimized and the selected similar patches are more accurate. Experimental results indicate the proposed algorithm achieves better restored results compared to the classical NLM's method.
基金supported by the Capital Medical Development Foundation(Grant No.2011-2015-02)the National Basic Research Program of China (973 Program)(Grant No.2011CB707705)the Capital Characteristic Clinical Application Research(Grant No.Z121107001012115)
文摘Objective： To assess if diffusion-weighted magnetic resonance （MR） imaging without apparent diffusion coefficient （ADC） values provides added diagnostic value in combination with conventional MR imaging in the detection and characterization of small nodules in cirrhotic liver. Methods： Two observers retrospectively and independently analyzed 86 nodules （_〈3 em） certified pathologically in 33 patients with liver cirrhosis, including 48 hepatocellular carcinoma （HCC） nodules, 13 high-grade dysplastic nodules （HDN）, 10 low-grade dysplastic nodules （LDNs） and 15 other benign nodules. All these focal nodules were evaluated with conventional MR images （Tl-weighted, T2-weighted and dynamic gadolinium-enhanced images） and breath-hold diffusion-weighted images （DWI） （b=500 s/mm2）. The nodules were classified by using a scale of 1-3 （1, not seen; 3, well seen） on DWI for qualitative assessment. These small nodules were characterized by two radiologists. ADC values weren＇t measured. The diagnostic performance of the combined DWI-conventional images and the conventional images alone was evaluated using receiver operating characteristic （ROC） curves. The area under the curves （Az）, sensitivity and specificity values for characterizing different small nodules were also calculated. Results： Among 48 HCC nodules, 33 （68.8%） were graded as 3 （well seen）, 6 （12.5%） were graded as 2 （partially obscured）, and 9 weren＇t seen on DWI. Among 13 HDNs, there were 3 （23.1%） and 4 （30.8%） graded as 3 and 2 respectively. Five （50%） of 10 benign nodules were partially obscured and slightly hyperintense. For 86 nodules, the average diagnostic accuracy of combined DWI-conventional images was 82.56%, which was increased significantly compared with conventional MR images with 76.17%. For HCC and HDN, the diagnostic accuracy of combined DWI-conventional images increased from 78.69% to 86.07 %. Conclusions： Diffusion-weighted MR imaging does provide added diagnostic value in the detection and characterization of HDN and HCC, and it may not be helpful for LDN and regenerative nodule （RN） in cirrhotic liver.
文摘Objective To assess the reproducibility of whole-body diffusion weighted imaging(WB-DWI) technique in healthy volunteers under normal breathing with background body signal suppression.Methods WB-DWI was performed on 32 healthy volunteers twice within two-week period using short TI inversion-recovery diffusion-weighted echo-planar imaging sequence and built-in body coil.The volunteers were scanned across six stations continuously covering the entire body from the head to the feet under normal breathing.The bone apparent diffusion coefficient(ADC) and exponential ADC(eADC) of regions of interest(ROIs) were measured.We analyzed correlation of the results using paired-t-test to assess the reproducibility of the WB-DWI technique.Results We were successful in collecting and analyzing data of 64 WB-DWI images.There was no significant difference in bone ADC and eADC of 824 ROIs between the paired observers and paired scans(P>0.05).Most of the images from all stations were of diagnostic quality.Conclusion The measurements of bone ADC and eADC have good reproducibility.WB-DWI technique under normal breathing with background body signal suppression is adequate.
基金Indian Institute of Technology,Kharagpur in India for supporting this work
文摘Particle size distribution of coarse aggregates through mechanical sieving gives results in terms of cumu- lative mass percent. But digital image processing generated size distribution of particles, while being fast and accurate, is often expressed in terms of area function or number of particles. In this paper, a mass model is developed which converts the image obtained size distribution to mass-wise distribution, mak- ing it readily comparable to mechanical sieving data. The concept of weight/particle ratio is introduced for mass reconstruction from 2D images of particle aggregates. Using this mass model, the effects of several particle shape parameters （such as major axis, minor axis, and equivalent diameter） on sieve-size of the particles is studied. It is shown that the sieve-size of a particle strongly depend upon the shape param- eters, 91% of its variation being explained by major axis, minor axis, bounding box length and equivalent diameter. Furthermore, minor axis gives an overall accurate estimate of particle sieve-size, error in mean size （D-50） being just 0.4%. However, sieve-size of smaller particles （〈20 ram） strongly depends upon the length of the smaller arm of the bounding box enclosing them and sieve-sizes of larger particles （〉20 mm） are highly correlated to their equivalent diameters. Multiple linear regression analysis has been used to generate overall mass-wise particle size distribution, considering the influences of all these shape parameters on particle sieve-size. Multiple linear regression generated overall mass-wise particle size distribution shows a strong correlation with sieve generated data. The adjusted R-square value of the regression analysis is found to be 99 percent （w.r,t cumulative frequency）. The method proposed in this paper provides a time-efficient way of producing accurate （up to 99%） mass-wise PSD using digital image processing and it can be used effectively to renlace the mechanical sieving.
基金This work is supported by the National Natural Science Foundation of China nos.11971215 and 11571156,MOE-LCSMSchool of Mathematics and Statistics,Hunan Normal University,Changsha,Hunan 410081,China.
文摘Regularization methods have been substantially applied in image restoration due to the ill-posedness of the image restoration problem.Different assumptions or priors on images are applied in the construction of image regularization methods.In recent years,matrix low-rank approximation has been successfully introduced in the image denoising problem and significant denoising effects have been achieved.Low-rank matrix minimization is an NP-hard problem and it is often replaced with the matrix’s weighted nuclear norm minimization(WNNM).The assumption that an image contains an extensive amount of self-similarity is the basis for the construction of the matrix low-rank approximation-based image denoising method.In this paper,we develop a model for image restoration using the sum of block matching matrices’weighted nuclear norm to be the regularization term in the cost function.An alternating iterative algorithm is designed to solve the proposed model and the convergence analyses of the algorithm are also presented.Numerical experiments show that the proposed method can recover the images much better than the existing regularization methods in terms of both recovered quantities and visual qualities.
基金funding from Prince Sattam bin Abdulaziz University through the Project Number(PSAU/2023/01/24607).
文摘In the domain ofmedical imaging,the accurate detection and classification of brain tumors is very important.This study introduces an advanced method for identifying camouflaged brain tumors within images.Our proposed model consists of three steps:Feature extraction,feature fusion,and then classification.The core of this model revolves around a feature extraction framework that combines color-transformed images with deep learning techniques,using the ResNet50 Convolutional Neural Network(CNN)architecture.So the focus is to extract robust feature fromMRI images,particularly emphasizingweighted average features extracted fromthe first convolutional layer renowned for their discriminative power.To enhance model robustness,we introduced a novel feature fusion technique based on the Marine Predator Algorithm(MPA),inspired by the hunting behavior of marine predators and has shown promise in optimizing complex problems.The proposed methodology can accurately classify and detect brain tumors in camouflage images by combining the power of color transformations,deep learning,and feature fusion via MPA,and achieved an accuracy of 98.72%on a more complex dataset surpassing the existing state-of-the-art methods,highlighting the effectiveness of the proposed model.The importance of this research is in its potential to advance the field ofmedical image analysis,particularly in brain tumor diagnosis,where diagnoses early,and accurate classification are critical for improved patient results.
基金supported by the National Natural Science Foundation of China(6140130861572063)+7 种基金the Natural Science Foundation of Hebei Province(F2016201142F2016201187)the Natural Social Foundation of Hebei Province(HB15TQ015)the Science Research Project of Hebei Province(QN2016085ZC2016040)the Science and Technology Support Project of Hebei Province(15210409)the Natural Science Foundation of Hebei University(2014-303)the National Comprehensive Ability Promotion Project of Western and Central China
文摘As synthetic aperture radar（SAR） has been widely used nearly in every field, SAR image de-noising became a very important research field. A new SAR image de-noising method based on texture strength and weighted nuclear norm minimization（WNNM） is proposed. To implement blind de-noising, the accurate estimation of noise variance is very important. So far, it is still a challenge to estimate SAR image noise level accurately because of the rich texture. Principal component analysis（PCA） and the low rank patches selected by image texture strength are used to estimate the noise level. With the help of noise level, WNNM can be expected to SAR image de-noising. Experimental results show that the proposed method outperforms many excellent de-noising algorithms such as Bayes least squares-Gaussian scale mixtures（BLS-GSM） method, non-local means（NLM） filtering in terms of both quantitative measure and visual perception quality.
文摘Summary： The chronological and spatial rules of changes during focal cerebral ischemia and reperfusion in different brain regions with magnetic resonance diffusion-weighted imaging （DWI） in a model of occlusion of middle cerebral artery （MCAO） and the development of cytotoxic edema in acute phase were explored. Fifteen healthy S-D rats with MCA occluded by thread-emboli were randomly divided into three groups. 15 min after the operation, the serial imaging was scanned on DWI for the three groups. The relative mean signal intensity （RMSI） of the frontal lobe, parietal lobe, lateral cauda-putamen, medial cauda-putamen and the volume of regions of hyperintense signal on DWI were calculated. After the last DWI scanning, T2WI was performed for the three groups. After 15 rain ischemia, the rats was presented hyperintense signals on DWI. The regions of hyperintense signal were enlarged with prolonging ischemia time. The regions of hyperintense signal were back to normal after 60 min reperfusion with a small part remaining to show hyperintense signal. The RMSIs of parietal lobe and lateral cauda-putamen were higher than that of the frontal lobe and medial cauda-putamen both in ischemia phase and recanalization phase. The three groups were normal on T2WI imaging. DWI had good sensitivity to acute cerebral ischemia, which was used to study the chronological and spatial rules of development of early cell edema in ischemia regions.
基金Project(2009AA04Z214) supported by the National High Technology Research and Development Program of ChinaProject(07JJ6133) supported by the Natural Science Foundation of Hunan Province, China
文摘To denoise the diffusion weighted images （DWls） featured as multi-boundary, which was very important for the calculation of accurate DTIs （diffusion tensor magnetic resonance imaging）, a modified Wiener filter was proposed. Through analyzing the widely accepted adaptive Wiener filter in image denoising fields, which suffered from annoying noise around the edges of DWIs and in turn greatly affected the denoising effect of DWIs, a local-shift method capable of overcoming the defect of the adaptive Wiener filter was proposed to help better denoising DWIs and the modified Wiener filter was constructed accordingly. To verify the denoising effect of the proposed method, the modified Wiener filter and adaptive Wiener filter were performed on the noisy DWI data, respectively, and the results of different methods were analyzed in detail and put into comparison. The experimental data show that, with the modified Wiener method, more satisfactory results such as lower non-positive tensor percentage and lower mean square errors of the fractional anisotropy map and trace map are obtained than those with the adaptive Wiener method, which in turn helps to produce more accurate DTIs.
基金Supported by National Natural Science Foundation of China (No.30500129)
文摘In order to avoid the influence of noise variance on the filtering performances, a modified adaptive weighted averaging (MAWA) filtering algorithm is proposed for noisy image sequences. Based upon adaptive weighted averaging pixel values in consecutive frames, this algorithm achieves the filtering goal by assigning smaller weights to the pixels with inappropriate estimated motion trajectory for noise. It only utilizes the intensity of pixels to suppress noise and accordingly is independent of noise variance. To evaluate the performance of the proposed filtering algorithm, its mean square error and percentage of preserved edge points were compared with those of traditional adaptive weighted averaging and non-adaptive mean filtering algorithms under different noise variances. Relevant results show that the MAWA filtering algorithm can preserve image structures and edges under motion after attenuating noise, and thus may be used in image sequence filtering.
文摘Medical linac based imaging modalities such as portal imaging can be utilized for highly accurate measurements. An intensity-weighted centroid method for determining object center is proposed that can detect the position of small object at subpixel accuracy. The principles and algorithms of the intensity-weighted centroid method are presented. Analytical results are derived for positional accuracy of a rod and a sphere in digital images, and the theoretical accuracy limits are calculated. The method was experimentally examined using phantoms with embedded ball bearings (BBs). Images of the phantoms were taken by the MV portal imager of a medical linac. The image pixel size was 0.26 mm when projected at the linac isocenter plane. The BB coordinates were calculated by applying the intensity-weighted centroid method after removing the background. The reproducibility of BB position detection was measured with 3 monitor unit (MU) exposures at various dose rates. A stationary BB, of 0.25 image contrast, showed position reproducibility in the range of 0.004 - 0.013 mm. When the method was used to measure the displacement of a moving BB, the difference between the measured and expected BB position had a standard deviation of 0.006 mm. The effect of image noise on the BB detection accuracy was measured using a phantom with multiple BBs. The overall detection accuracy, represented by standard deviation, steadily improved from 0.13 mm at 0.03 MU to 0.008 mm at 5.0 MU, and showed an inverse correlation with contrast-to-noise ratio. We demonstrated that intensity-weighted centroid method can achieve subpixel accuracy in position detection. With a linac based imaging system, precise mechanical measurement with accuracy of microns could be achieved.
文摘BACKGROUND Cutaneous melanoma is an aggressive skin cancer with high metastatic potential.Accurate staging is critical to guide therapeutic strategies and improve prognosis.Whole-body magnetic resonance imaging(WB-MRI),particularly when combined with diffusion-weighted imaging(DWI),has emerged as promising tool for comprehensive,radiation-free assessment of metastatic spread.AIM To systematically review the diagnostic performance and clinical utility of WBMRI in the staging and restaging of cutaneous melanoma,with comparison to conventional imaging modalities such as computed tomography(CT)and positron emission tomography/CT(PET/CT).METHODS A systematic literature review was conducted using PubMed,Embase,Scopus and Web of Science databases for studies published in the last 10 years.Inclusion criteria focused on comparative diagnostic accuracy studies of WB-MRI vs CT and PET/CT for melanoma staging.The methodological quality of the studies was appraised using the QUADAS-2 tool.RESULTS Sixteen studies involving over 700 patients met the inclusion criteria.WB-MRI showed high sensitivity(73%-90%)and specificity(up to 98%)in detecting metastases,particularly in bone,liver and soft tissue.DWI enhanced lesion detection,and WB-MRI often influenced clinical management decisions.However,CT outperformed WB-MRI in identifying small pulmonary nodules.AI-assisted analysis and contrastenhanced sequences further improved diagnostic confidence.CONCLUSION WB-MRI represents a robust imaging modality for staging cutaneous melanoma,offering superior soft-tissue contrast and functional imaging without ionizing radiation.Its strengths lie in detecting bone,liver and brain metastases.Challenges include limited lung lesion detection,cost,and availability.Advances in artificial intelligence,Hybrid PET/MRY systems,and radiomics are poised to expand WB-MRI’s role in personalized melanoma management.
